Practical decisions for AI and software
Technical guides to choose models, verify software and plan delivery.
Search every article
Search the full article text.
No posts match your search. Try another term or pick a topic.
Latest articles
New comparisons, practical guides and engineering lessons.
AI & AgentsAnthropic Says No Open-Weights Ban. The Cost War Is Still Real.
Anthropic explicitly rejects a protectionist open-weights ban while seeking action against illicit industrial distillation. What its policy, Coinbase's first-party cost report, and EU rules actually mean for buyers.
Delivery & QAAgile De-engineering
How a movement built to liberate engineers came to erode engineering culture in the enterprise. Alexandre Kotcherguine and Kevin Riedl trace the commercialisation, ritual capture, metric inversion, and craft erosion behind it.
AI & AgentsWhat an Internal AI Assistant Actually Costs in the DACH Region (2026)
Embeddings, vector DB, tokens, hosting, and the maintenance line everyone forgets. A directional per-seat cost breakdown for a DACH internal AI assistant.
Product & MVPThe MVP Is Dead. Build a Minimum Credible Product.
AI can reduce prototype effort, not the need for product judgment. Avoidable roughness may damage the signal an MVP should collect. A practical case for less scope, one trustworthy path, and decision-grade evidence.
AI & AgentsLLM Gateways Compared 2026: LiteLLM vs OpenRouter vs Portkey vs RouteLLM
One endpoint over many providers, with fallback, caching, spend limits, and routing in one place. How LiteLLM, OpenRouter, Portkey, and RouteLLM differ, and how to choose on the constraint that binds you.
AI & AgentsSelf-Hosting LLMs in the EU: When Open Weights Actually Pay Off
The GPU is the cheap part. Here is the real cost of self-hosting open weights, a defensible break-even formula, the GDPR trade-offs, and the vLLM production stack.
AI & AgentsOpen-Weight LLMs 2026: DeepSeek, Qwen, Kimi, GLM, Llama and Muse
Compare open-weight LLMs in October 2026: DeepSeek, Qwen, Kimi, GLM, Llama and Muse. Exact licenses, local versus cluster hardware and evaluation criteria.
Business & RegulationAI Consulting in Austria 2026: An Honest Guide for SMEs
AI consulting in Austria: realistic scoping costs, SME use cases, AI Act duties and October 2026 funding status, including the end of KMU.DIGITAL.
AI & AgentsThe Bottleneck Was Never Intelligence. It Was Context.
Rakuten reported a seven-hour Claude Code session on vLLM with 99.9% numerical accuracy for one method. What the vendor case study shows, what it does not, and how to build a reviewable agent workflow.
Get the next field note
One concise email when we publish. No tracking pixels, and no inbox filler.